Selectively authenticating a user using voice recognition and random representations

Abstract

Techniques are described herein that are capable of selectively authenticating a user using voice recognition and random representations. A credential that is received from an entity is compared to a reference credential associated with a user. The random representations are caused to be displayed to the entity based at least in part on the credential corresponding to the reference credential. Each random representation has a random entropy. A representation of speech of the entity is analyzed to determine whether a voice characterized by the speech corresponds to a voice profile that characterizes a voice of the user and to determine whether the speech includes a verbal identification of each random representation. The user is selectively authenticated based at least in part on whether the voice corresponds to the voice profile and further based at least in part on whether the speech includes the verbal identification of each random representation.

What is claimed is: 
     
         1 . A system to selectively authenticate a user using voice recognition and random representations, the system comprising:
 a memory; and   one or more processors coupled to the memory, the one or more processors configured to:
 compare a credential that is received from an entity to a reference credential that is associated with the user to determine whether the credential corresponds to the reference credential; 
 cause the random representations to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random representation having a random entropy; 
 analyze a representation of speech of the entity to determine whether a voice that is characterized by the speech corresponds to a voice profile that characterizes a voice of the user and to determine whether the speech includes a verbal identification of each random representation; and 
 selectively authenticate the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the verbal identification of each random representation. 
   
     
     
         2 . The system of  claim 1 , wherein the one or more processors are configured to:
 cause random alphanumeric representations to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random alphanumeric representation having a random entropy, each random alphanumeric representation including one or more alphanumeric characters;   analyze the representation of the speech of the entity to determine whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and to determine whether the speech includes a reading of each random alphanumeric representation; and   selectively authenticate the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the reading of each random alphanumeric representation.   
     
     
         3 . The system of  claim 2 , wherein the one or more processors are configured to:
 cause random words to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random word having a random entropy;   analyze the representation of the speech of the entity to determine whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and to determine whether the speech includes a reading of each random word; and   selectively authenticate the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the reading of each random word.   
     
     
         4 . The system of  claim 2 , wherein the one or more processors are configured to:
 cause a random number, which includes a plurality of random digits in a designated order, to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random digit of the plurality of random digits having a random entropy;   analyze the representation of the speech of the entity to determine whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and to determine whether the speech includes a recitation of the random digits in the designated order; and   selectively authenticate the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the recitation of the random digits in the designated order.   
     
     
         5 . The system of  claim 4 , wherein the recitation of the random digits in the speech includes a recitation of the random number as a whole, rather than a recitation of the random digits as independent numbers. 
     
     
         6 . The system of  claim 1 , wherein the one or more processors are configured to:
 analyze an encrypted hypertext transfer protocol secure (HTTPS) browser communication, which represents the speech of the entity, to determine whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and to determine whether the speech includes the verbal identification of each random representation.   
     
     
         7 . The system of  claim 1 , wherein the one or more processors are configured to:
 cause the random representations to be displayed to the entity at a time instance; and   selectively authenticate the user further based at least in part on whether the representation of the speech of the entity is received within a specified period of time that begins at the time instance.   
     
     
         8 . The system of  claim 1 , wherein the one or more processors are configured to:
 analyze the representation of the speech of the entity to determine whether a cadence of the speech of the entity corresponds to a reference cadence that is associated with the user; and   selectively authenticate the user further based at least in part on whether the cadence of the speech of the entity corresponds to the reference cadence that is associated with the user.   
     
     
         9 . The system of  claim 8 , wherein the one or more processors are further configured to:
 store a representation of the reference cadence in a secure enclave of a machine that is associated with the user or in a secure enclave of a browser that is configured to execute on the machine.   
     
     
         10 . The system of  claim 1 , wherein the one or more processors are further configured to:
 store the voice profile that characterizes the voice of the user in a secure enclave of a server.   
     
     
         11 . The system of  claim 1 , wherein the one or more processors are configured to:
 not authenticate the user based at least in part on the voice that is characterized by the speech not corresponding to the voice profile that characterizes the voice of the user;   establish a risk score associated with the user, the risk score indicating a likelihood that another user is to attempt to access an account associated with the user; and   increase the risk score associated with the user based at least in part on the voice that is characterized by the speech not corresponding to the voice profile that characterizes the voice of the user.   
     
     
         12 . The system of  claim 11 , wherein the one or more processors are configured to:
 determine that the voice that is characterized by the speech corresponds to a second voice profile that characterizes a voice of a second user who is different from the user; and   increase the risk score associated with the user based at least in part on the voice that is characterized by the speech corresponding to the second voice profile that characterizes the voice of the second user.   
     
     
         13 . A method of selectively authenticating a user using voice recognition and random representations, the method implemented by a computing system, the method comprising:
 receiving a credential from an entity;   comparing the credential to a reference credential that is associated with the user to determine whether the credential corresponds to the reference credential;   causing the random representations to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random representation having a random entropy;   analyzing a representation of speech of the entity to determine whether a voice that is characterized by the speech corresponds to a voice profile that characterizes a voice of the user and to determine whether the speech includes a verbal identification of each random representation; and   selectively authenticating the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the verbal identification of each random representation.   
     
     
         14 . The method of  claim 13 , wherein causing the random representations to be displayed comprises:
 causing random pictures to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random picture having a random entropy;   wherein analyzing the representation of the speech of the entity comprises:
 analyzing the representation of the speech of the entity to determine whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and to determine whether the speech includes a description of each random picture; and 
   wherein selectively authenticating the user comprises:
 selectively authenticating the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the description of each random picture. 
   
     
     
         15 . The method of  claim 13 , wherein causing the random representations to be displayed comprises:
 causing random symbols to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random symbol having a random entropy, each random symbol not being a number and not being a letter in an alphabet;   wherein analyzing the representation of the speech of the entity comprises:
 analyzing the representation of the speech of the entity to determine whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and to determine whether the speech includes a description of each random symbol; and 
   wherein selectively authenticating the user comprises:
 selectively authenticating the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the description of each random symbol. 
   
     
     
         16 . The method of  claim 13 , wherein the random representations comprise at least five random representations. 
     
     
         17 . The method of  claim 13 , wherein receiving the credential from the entity comprises:
 receiving the credential via a first website that is displayed to the entity; and   wherein causing the random representations to be displayed to the entity comprises:
 redirecting the entity to a second website that presents the random representations to the entity. 
   
     
     
         18 . The method of  claim 13 , wherein causing the random representations to be displayed to the entity comprises:
 causing the random representations to be displayed to the entity via an encrypted hypertext transfer protocol secure (HTTPS) browser communication.   
     
     
         19 . The method of  claim 13 , further comprising:
 utilizing the representation of the speech of the entity in a training set for a machine learning-based voice recognition model.   
     
     
         20 . The method of  claim 13 , further comprising:
 storing the voice profile that characterizes the voice of the user in a secure enclave of a machine that is associated with the user or in a secure enclave of a browser that is configured to execute on the machine.   
     
     
         21 . The method of  claim 13 , further comprising:
 causing a textual passage to be displayed to the user;   instructing the user to read from the textual passage;   recording audio of the user reading from the textual passage for at least a designated duration of time to provide a voice recording; and   generating the voice profile that characterizes the voice of the user from the voice recording.   
     
     
         22 . A computer program product comprising a computer-readable storage medium having instructions recorded thereon for enabling a processor-based system to selectively authenticate a user using voice recognition and random representations by performing operations, the operations comprising:
 comparing a credential that is received from an entity to a reference credential that is associated with the user to determine whether the credential corresponds to the reference credential;   causing the random representations to be displayed to the entity based at least in part on the credential corresponding to the reference credential, each random representation having a random entropy;   analyzing a representation of speech of the entity to determine whether a voice that is characterized by the speech corresponds to a voice profile that characterizes a voice of the user and to determine whether the speech includes a verbal identification of each random representation; and   selectively authenticating the user based at least in part on whether the voice that is characterized by the speech corresponds to the voice profile that characterizes the voice of the user and further based at least in part on whether the speech includes the verbal identification of each random representation.